EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Rumor detection on social networks based on Temporal Tree Transformer

Sirong Wu, Yuhui Deng iD, Junjie Liu, Xi Luo, Gengchen Sun

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0320333 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2025. Verfasst von Sirong Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Provincial Key Laboratoryof Interdisciplinary Research and Application for Data Science, Beijing NormalUniversity-Hong Kong Baptist Univers…. Hauptthemen laut MEDLINE: Social Media, Social Networking. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EUROPEAN HORIZON.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid propagation of rumors on social media can give rise to various social issues, underscoring the necessity of swift and automated rumor detection. Existing studies typically identify rumors based on their textual or static propagation structural information, without considering the dynamic changes in the structure of rumor propagation over time. In this paper, we propose the Temporal Tree Transformer model, which simultaneously considers text, propagation structure, and temporal changes. By analyzing observing the growth of propagation tree structures in different time windows, we use Gated Recurrent Unit (GRU) to encode these trees to obtain better representations for the classification task. We evaluate our model’s performance using the PHEME dataset. In most existing studies, information leakage occurs when conversation threads from all events are randomly divided into training and test sets. We perform Leave-One-Event-Out (LOEO) cross-validation, which better reflects real-world scenarios. The experimental results show that our model achieves state-of-the-art accuracy 75.84% and Macro F1 score of 71.98%, respectively. These results demonstrate that extracting temporal features from propagation structures leads to improved model generalization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Social MediaSocial NetworkingHumansAlgorithmsModels, Theoretical

Autor:innen und Institutionen

  • Guangdong Provincial Key Laboratoryof Interdisciplinary Research and Application for Data Science, Beijing NormalUniversity-Hong Kong Baptist University United International College, Zhuhai,Guangdong Province, China.
  • Department of Statistics and Data Science, Faculty ofScience and Technology, Beijing Normal University-Hong Kong Baptist UniversityUnited International College, Zhuhai, Guangdong Province, China.
  • Faculty of Science,Hong Kong Baptist University, Hong Kong, China.
  • Department of PoliticalScience, Trinity College Dublin, Dublin 2, Ireland.
  • Department of Statistics andActuarial Science, Faculty of Science, The University of Hong Kong, Hong Kong,China.

ORCID-Profile: Yuhui Deng

Förderung

  • EUROPEAN HORIZON

Zitieren

APA

Wu, S., Deng, Y., Liu, J., Luo, X., & Sun, G. (2025). Rumor detection on social networks based on Temporal Tree Transformer. PLOS ONE. https://doi.org/10.1371/journal.pone.0320333

Vancouver

Wu S, Deng Y, Liu J, Luo X, Sun G. Rumor detection on social networks based on Temporal Tree Transformer. PLOS ONE. 2025. doi:10.1371/journal.pone.0320333

BibTeX
@article{Wu2025,
  author = {Wu, Sirong and Deng, Yuhui and Liu, Junjie and Luo, Xi and Sun, Gengchen},
  title = {Rumor detection on social networks based on Temporal Tree Transformer},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0320333}
}
Kostenlos starten →